YouTube transcripts,
delivered to your n8n Webhook node

Subscribe to a channel. When it posts a new video, TranscriptHook sends one POST to your n8n workflow with the video details, the full transcript text and timestamped segments. No YouTube API key, no OAuth, no polling code.

Channels are checked about every 10 minutes. Free plan, no card.

n8n's YouTube node doesn't return transcripts

The YouTube node gives you metadata: title, description, view count. It does not give you the spoken text of a video. To get that, you would normally set up a Google Cloud project, handle OAuth and quota, write polling logic, and find a way to pull captions.

TranscriptHook does that part. It reads each channel's public RSS feed, waits for YouTube to publish captions, and posts a JSON payload to the Webhook node you already have in n8n. There is no native TranscriptHook node. You use the standard Webhook node.

The pattern: new video detected, TranscriptHook posts to your Webhook node, downstream nodes do the work (LLM, Slack, Notion, a database, anything).
Before you build on this
  • Not real time. Channels are checked about every 10 minutes (Free accounts can take up to about 20). Then the webhook waits for YouTube to publish captions. Expect minutes, sometimes longer. If you need a video the second it goes live, this is the wrong tool.
  • Missing captions. A video without captions is held and retried for up to 24 hours. After that it is sent with transcript.available set to false. A video that never gets captions cannot match a keyword filter, so it is not pushed.
  • Starts from now. A new subscription starts from the channel's latest video. Older videos are not imported.
  • Retries over about a day. If your endpoint fails, TranscriptHook retries at 2s, 10s and 30s, then up to five more times over roughly 25 hours. Use the Pull API to catch up after a longer outage.
  • Signed deliveries. Every request carries an X-VidProxy-Signature header you can verify with a Code node (see Verifying webhook signatures). Verifying is optional; still keep the n8n path unguessable.
  • Free and Starter only. Pro and Agency are listed but cannot be bought yet.

Connect TranscriptHook to n8n in three steps

No code. Point the two services at each other.

1

Add a Webhook node in n8n

In your workflow, add a Webhook trigger node. Set the HTTP method to POST and copy the Production URL. It looks like https://your-n8n.domain/webhook/[id]. The Test URL only works while you are listening for a test event in the editor.

2

Add the channel in TranscriptHook

In the dashboard, click Add channel. Paste the channel URL or @handle, paste the n8n URL as the webhook, and give it a label (it shows up as subscription.label). Then open the subscription's Edit modal and click Send test. It posts a sample payload to your Webhook node so you can map fields before any real video arrives.

3

Build from the payload

Activate the workflow. Use {{ $json.body.transcript.text }}, {{ $json.body.video.title }} and the other fields in any node after the trigger. The Webhook node puts the JSON under body, so the fields live at $json.body.transcript.text and so on.

TranscriptHook reads the channel's public RSS feed, so there is no YouTube API key, OAuth setup or quota to manage. A new subscription starts from the channel's latest video.

What your n8n Webhook node receives

The fields in the webhook payload, as n8n expression paths.

// n8n expression paths for common fields

// Video info
{{ $json.body.video.title }}          // "Weekly market wrap"
{{ $json.body.video.url }}            // "https://www.youtube.com/watch?v=e2evid2"
{{ $json.body.video.published }}      // "2026-10-02T18:25:51.939Z"
{{ $json.body.video.description }}    // Full YouTube description, often with links (null on older videos)

// Channel info
{{ $json.body.subscription.channel_name }}   // "Market Brief Weekly"
{{ $json.body.subscription.label }}          // Your subscription label

// Transcript
{{ $json.body.transcript.available }}        // true / false
{{ $json.body.transcript.text }}             // Full plain-text transcript
{{ $json.body.transcript.segments }}         // Array of {start, duration, text}

// Only when you set keyword filters
{{ $json.body.matched_keywords }}            // e.g. ["tariffs"]

Add an IF node on {{ $json.body.transcript.available }} right after the trigger, so videos without captions go to a log step and not to your LLM node.

Workflows you can build

You assemble these in n8n from the payload. TranscriptHook only supplies the trigger data.

Channel digest in Slack

Webhook node → IF node (transcript.available is true) → LLM node (write a five-line summary from transcript.text) → Slack node (post the summary with video.url).

Keyword watch to a sheet or CRM

Set keyword filters on the subscription, for example a competitor name or "pricing". The workflow only runs for videos whose transcript matched. Write matched_keywords, video.title, video.url and the first matching segment to Airtable, Notion or Google Sheets. Keyword filters and alerts are on every plan.

Transcript to Notion

Webhook node → Notion node (create a database page). Map video.title to Name, video.url to a URL property and transcript.text to the page content.

Transcript to Airtable research log

Webhook node → OpenAI node (pick a category from transcript.text) → Airtable node (create a record with the video metadata and the category).

Summary by email

Webhook node → OpenAI node (summarize or draft a post from transcript.text) → Gmail or SMTP node (send to your team or list).

Transcript to vector store

Webhook node → Code node (chunk transcript.segments, keeping start so you can link back to the moment in the video) → embeddings node → vector store node. Your retrieval workflow can then answer with a timestamped source.

What you can run on each plan

Free: $0, no card. 1 channel, 1 webhook, 10 on-demand lookups.

Starter: $9 a month. 15 channels, 3 webhooks, 500 lookups per month.

Keyword filters, keyword alerts and the MCP server are on every plan. Monitored channels never use lookups. A lookup credit is used only when an on-demand fetch returns a transcript. Some competitors charge a credit per monitor check. TranscriptHook has no per-check credits, only on-demand lookups. Pro and Agency are not available yet.

Common questions

Do I need a YouTube API key or OAuth?
No. TranscriptHook detects new videos from each channel's public RSS feed, so there is no Google Cloud project, consent screen or quota on your side.
Does TranscriptHook work with self-hosted n8n?
Yes. TranscriptHook just needs a publicly accessible webhook URL. If your n8n instance is behind a VPN or on localhost, use a tunnel like ngrok to expose it temporarily for testing, or deploy n8n to a VPS with a public URL for production use.
Can I test my webhook before going live?
Yes. The subscription's Edit modal has a Send test button. It posts one sample payload ({ event: "test", test: true, ... } with placeholder video and subscription data) to your webhook URL, even before you save the subscription. It uses the same delivery path as a real webhook but makes a single attempt with no retry, so you can check your n8n Webhook node before a real video arrives.
How do I handle the case where transcript.available is false?
Add an IF node right after the Webhook node. Condition: {{ $json.body.transcript.available }} equals true. Send the true path to your processing nodes and the false path to a log step. If a video has no captions, TranscriptHook holds it and retries for up to 24 hours, then sends the webhook with transcript.available set to false, so your workflow still sees the event.
Can I have multiple n8n workflows triggered by different channels?
Yes. Point each subscription at a different n8n Webhook URL, or point several subscriptions at one URL and branch with a Switch node on subscription.label or subscription.channel_name. Free has 1 webhook endpoint and Starter has 3, so on those plans the Switch node is the usual route.
What if my n8n server is down when TranscriptHook fires the webhook?
TranscriptHook retries a failed webhook at 2, 10 and 30 seconds after the first attempt, then up to five more times over roughly a day (about 10 minutes, 30 minutes, 2 hours, 6 hours and 16 hours later, on our polling cycle). If every attempt fails, the delivery is marked failed in the delivery log and a badge shows on the subscription card. After an outage longer than that, use the Pull API to catch up on anything you missed.
How soon after a video publishes does the workflow run?
Two waits add up. TranscriptHook checks channels about every 10 minutes (Free accounts can take up to about 20). Then the webhook waits for YouTube to publish captions, which varies. Expect minutes, sometimes longer. If captions are still missing after 24 hours, the webhook is sent with transcript.available set to false.
Does a monitored video use up my lookup credits?
No. Videos from monitored channels never use lookups. Lookups are for on-demand fetches, and a lookup credit is used only when a transcript is actually returned.
How many channels can I feed into n8n?
Free allows 1 channel and 1 webhook. Starter ($9 a month) allows 15 channels and 3 webhooks. Pro and Agency are listed but cannot be bought yet. With 15 channels and 3 webhook URLs, the usual setup is one n8n workflow with a Switch node on subscription.label.

Add YouTube transcripts to your n8n workflows

Free includes 1 channel, 1 webhook and 10 lookups. Starter is $9 a month for 15 channels.

No credit card · Free plan